{"id":"W3184920851","doi":"10.48550/arxiv.2107.13505","title":"Deep Recurrent Semi-Supervised EEG Representation Learning for Emotion Recognition","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Autoencoder; Artificial intelligence; Computer science; Machine learning; Electroencephalography; Unsupervised learning; Pattern recognition (psychology); Deep learning; Benchmark (surveying); Supervised learning; Context (archaeology); Semi-supervised learning; Feature learning; Artificial neural network; Psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001044932,0.001033148,0.000830891,0.0004131107,0.0002270382,0.0005532886,0.001342301,0.0006201643,0.001518598],"category_scores_gemma":[0.003477437,0.000405237,0.0008961975,0.0004163399,0.0005403406,0.001091779,0.0009205302,0.001508872,0.0009108807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004223744,"about_ca_system_score_gemma":0.0005995238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002075355,"about_ca_topic_score_gemma":0.0041754,"domain_scores_codex":[0.9993567,0.0002535247,0.00003477672,0.0001915463,0.0000988245,0.00006462479],"domain_scores_gemma":[0.9986103,0.0005696758,0.000178434,0.0002807311,0.0003079866,0.00005289879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006885696,0.0005054275,0.003219359,0.000291347,0.0003320072,0.0001592954,0.0002637622,0.3340211,0.05016337,0.005029265,0.008839435,0.596487],"study_design_scores_gemma":[0.000007025175,0.00003531643,0.0006376564,0.000006840286,0.00001368036,0.00002647852,0.000009255437,0.9902539,0.005990947,0.002691271,0.0003194396,0.000008168144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04281172,0.000449879,0.9524403,0.0001799336,0.00004890087,0.0000488441,0.0002822899,0.002809323,0.0009289078],"genre_scores_gemma":[0.7992052,0.0003328091,0.193986,0.0002013465,0.0001003863,0.0001748882,0.002095162,0.000298752,0.003605451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002075355,"threshold_uncertainty_score":0.005526185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1426205121535089,"score_gpt":0.2413952445168076,"score_spread":0.09877473236329876,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}